Frequency-Domain Fusion Transformer for Image Inpainting
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911018983096320 |
|---|---|
| author | He, Sijin Lin, Guangfeng Li, Tao Chen, Yajun |
| author_facet | He, Sijin Lin, Guangfeng Li, Tao Chen, Yajun |
| contents | Image inpainting plays a vital role in restoring missing image regions and supporting high-level vision tasks, but traditional methods struggle with complex textures and large occlusions. Although Transformer-based approaches have demonstrated strong global modeling capabilities, they often fail to preserve high-frequency details due to the low-pass nature of self-attention and suffer from high computational costs. To address these challenges, this paper proposes a Transformer-based image inpainting method incorporating frequency-domain fusion. Specifically, an attention mechanism combining wavelet transform and Gabor filtering is introduced to enhance multi-scale structural modeling and detail preservation. Additionally, a learnable frequency-domain filter based on the fast Fourier transform is designed to replace the feedforward network, enabling adaptive noise suppression and detail retention. The model adopts a four-level encoder-decoder structure and is guided by a novel loss strategy to balance global semantics and fine details. Experimental results demonstrate that the proposed method effectively improves the quality of image inpainting by preserving more high-frequency information. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_18437 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Frequency-Domain Fusion Transformer for Image Inpainting He, Sijin Lin, Guangfeng Li, Tao Chen, Yajun Computer Vision and Pattern Recognition Image inpainting plays a vital role in restoring missing image regions and supporting high-level vision tasks, but traditional methods struggle with complex textures and large occlusions. Although Transformer-based approaches have demonstrated strong global modeling capabilities, they often fail to preserve high-frequency details due to the low-pass nature of self-attention and suffer from high computational costs. To address these challenges, this paper proposes a Transformer-based image inpainting method incorporating frequency-domain fusion. Specifically, an attention mechanism combining wavelet transform and Gabor filtering is introduced to enhance multi-scale structural modeling and detail preservation. Additionally, a learnable frequency-domain filter based on the fast Fourier transform is designed to replace the feedforward network, enabling adaptive noise suppression and detail retention. The model adopts a four-level encoder-decoder structure and is guided by a novel loss strategy to balance global semantics and fine details. Experimental results demonstrate that the proposed method effectively improves the quality of image inpainting by preserving more high-frequency information. |
| title | Frequency-Domain Fusion Transformer for Image Inpainting |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2506.18437 |